Goodness-Of-Fit Testing In The Presence Of Nuisance Parameters With Applications To Feature Selection And Pattern Recognition In Digital Image Processing

1988 ◽  
Author(s):  
Nicholas A. Nechval
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Feature Selection ◽  
Digital Image Processing ◽  
Digital Image ◽  
Goodness Of Fit ◽  
Nuisance Parameters ◽  
Goodness Of Fit Testing ◽  
Fit Testing

scholarly journals AN OPTIMIZED SURF-BASED FIRE AND SMOKE DETECTION SYSTEM USING IMAGE PROCESSING FROM SURVEILLANCE VIDEO.

2020 ◽  
Vol 9 (10) ◽  
pp. 86-96
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Feature Selection ◽  
Digital Image Processing ◽  
Digital Image ◽  
Optimization Approach ◽  
Surveillance Video ◽  
Smoke Detection ◽  
Video Frames ◽  
Optimal Feature

Over the last decades, digital image processing based fire and smoke detection have been improving steadily to provide a more accurate detection results in the area of surveillance security system. Detection of the fire and smoke from the surveillance videos is very challenging task due to the complex structural properties of the video frames or images and need improvisation in the existing work by utilization of feature selection or optimization approach to select on optimal feature according to the fire and smoke. A research based on the combination of various feature extraction techniques with feature selection approach for fire and smoke detection has been presented in this paper. In this research, we develop Fire and Smoke Detection (FSD) system using digital image processing with the concept of Speed up Robust Feature (SURF) along with the Intelligent Water Drops (IWD) as a feature selection and optimization algorithm. Here, Artificial Neural Network (ANN) is used as an Artificial Intelligence (AI) technique with that helps to select a set of optimal feature from the extracted by SURF descriptor from the video frames. By utilizing the concept of optimized ANN, the accuracy of proposed FSD system is increases in terms of detection accuracy and with minimum percentage of error. At last, the performance of the FSD system is calculated to validate the model and this shows that it is possible to use IWD with SURF as a feature extraction technique in order to detect the fire or smoke form the surveillance video with minimum error rate and the simulation results clearly show the effectiveness of proposed FSD system

scholarly journals Classification of Sambas Traditional Fabric “Kain Lunggi” Using Texture Feature

2019 ◽  
Vol 13 (4) ◽  
pp. 389
Author(s):  
Alda Cendekia Siregar ◽  
Barry Ceasar Octariadi
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Feature Selection ◽  
Digital Image Processing ◽  
Digital Image ◽  
Classification Accuracy ◽  
Selection Process ◽  
Image Features ◽  
K Value ◽  
Feature Extraction Method

Traditional fabric is a cultural heritage that has to be preserved. Kain Lunggi is Sambas traditional fabric that saw a decline in its crafter. To introduce Kain Lunggi in a broader national and global society in order to preserve it, a digital image processing based system to perform Kain Lunggi pattern recognition need to be built. Feature extraction is an important part of digital image processing. The visual feature that does not represent the character of an object will affect the accuracy of a recognition system. The purposes of this research are to perform feature selection on sets of feature to determine the best feature that can increase recognition accuracy. This research conducted in several steps which are image acquisition of Kain Lunggi pattern, preprocessing to reduce image noise, feature extraction to obtain image features, and feature selection. GLCM is implemented as a feature extraction method.  Feature extraction result will be used in a feature selection process using CFS (Correlation-based Feature Selection) methods. Selected features from CFS process are Angular Second Moment, Contrast, and Correlation. Selected features evaluation is conducted by calculating classification accuracy with the KNN method. Classification accuracy prior to feature extraction is 85.18% with K values K=1 ; meanwhile, the accuracy increases to 88.89% after feature selection. The highest accuracy improvement of 20.74% in KNN occurred when using K value K= 4.

scholarly journals Performance Analysis of Different Filters for Digital Image Processing

2021 ◽  
Vol 12 (2) ◽  
pp. 2572-2576
Author(s):  
Ch. Kavya , Et. al.
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Pattern Recognition ◽  
Digital Image Processing ◽  
Digital Image ◽  
High Frequency ◽  
Satellite Remote Sensing ◽  
Low Frequency ◽  
Linear Filters

Digital image processing is one of the drastically growing areas used in various real- time industries like medical, satellite, remote sensing, and pattern recognition. The output of the image processing depends on the quality of the image. Filters are used to modify the images, such as removing the noise and smoothing the images. It is essential to suppress the high- frequency values in the image for smoothening and improving the low-frequency values to enhance the image of strengthening else it doesn't provide good output. This paper discussed various filters and their functionalities concerning digital image processing. Here linear, as well as non-linear filters, are presented. It is easy to decide about the better filter for improving the image processing output from the discussion.

Sign in / Sign up

Export Citation Format

Share Document